A recent study published in Science Translational Medicine on Feb. 2 suggests that the combined use of blood lipid profiles and artificial intelligence may be effective in detecting early-stage lung cancer. The study comes from a Chinese research team that found a link between altered blood lipid levels and early-stage lung cancer, which they then used to create a mass spectrometry-based blood lipid test called the Lung Cancer Artificial Intelligence Detector (LCAID) v2.0.
The team used 10x Genomics’ droplet-based technology to perform single-cell RNA sequencing to profile metabolism-related transcriptional features across nearly 26,700 individual cells isolated from five patients awaiting treatment for non-small cell lung cancer (NSCLC) tumors. They then compared the profiles to new and published scRNA-seq profiles on 55,860 individual cells from eight healthy lung samples.
The researchers found that the LCAID v.2.0 set had 100 percent specificity in an initial validation cohort made up of 139 persons (99 of whom did have cancer and 40 of whom did not). They then assessed the approach using samples collected from 1,036 participants in a low-dose computed tomography lung cancer screening program run by a local hospital along with prospective samples from 109 individuals. The results: Sensitivity of 90 percent for detecting early-stage lung cancer, and a specificity of 92 percent.
The LCAID v2.0 is just one of the recent string of promising projects advancing blood-based early-stage lung cancer detection, a concept once dismissed as nothing but a pipe dream.
Learn more in Diagnostic Testing & Emerging Technologies.